# automl/Auto-PyTorch

Automatic architecture search and hyperparameter optimization for PyTorch

Repository: https://github.com/automl/Auto-PyTorch
Canonical: https://ross.abutalabs.com/products/auto-pytorch
Language: Python
License: Apache-2.0
License Family: permissive
Topics: automl, deep-learning, tabular-data, pytorch
Last push: 2024-04-09T06:17:08+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2833, "days_push": 876, "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 2541, forks 302 (observed 2026-08-28T04:06:59.421698+00:00)

## What it is
Auto-PyTorch is an AutoML framework that jointly performs neural architecture search and hyperparameter optimization for PyTorch models, using SMAC and multi-fidelity meta-learning. It primarily targets tabular classification/regression and time series forecasting tasks.

## Use cases
- automatically find the best neural network architecture for my tabular dataset
- hyperparameter optimization for a PyTorch model without manual tuning
- automated deep learning for classification and regression on tabular data
- auto-tune a deep learning model for time series forecasting
- compare automated deep learning pipelines against sklearn baselines

## When to choose
- you want fully automated deep learning on tabular or time series data
- you need joint architecture search and hyperparameter optimization with SMAC
- you prefer a research-grade AutoML tool built on PyTorch

## When to avoid
- you need image, text, or other non-tabular data support
- you want a rapidly evolving tool with frequent releases
- you need lightweight manual control over model architecture

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, deep-learning, data-science
- platform: python
- tags: automl, neural-architecture-search, hyperparameter-optimization, tabular-data, time-series-forecasting, smac, pytorch

## Member repositories
- automl/Auto-PyTorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:59.421698+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 2026-08-30T02:25:07.797520+00:00, confidence not recorded.
  - readme: https://github.com/automl/Auto-PyTorch (fetched 2026-08-28T04:06:59.421698+00:00, sha cc9d007ada77)
- Data as of 2026-08-30T08:39:29.467469+00:00.