AutoPyTorch

Automatic architecture search and hyperparameter optimization for PyTorch.

github.com/automl/Auto-PyTorch
AutoPyTorch homepage screenshot

About AutoPyTorch

Auto-PyTorch is an open-source tool that jointly optimizes neural network architecture and training hyperparameters for PyTorch to enable automated deep learning. It uses SMAC for optimization with Hyperband budget rules, portfolio warm-starting, and ensemble building from evaluated configurations.

It is mainly developed for tabular classification and regression and time series forecasting. Version 0.1.0 breaks compatibility with v0.0.2, and forecasting use requires additional dependencies.

Key features

  • Jointly optimizes network architecture and training hyperparameters
  • Supports tabular classification and regression tasks
  • Supports time series forecasting tasks
  • Warm-starts SMAC search with greedy portfolio
  • Builds ensemble from evaluated configurations
  • Processes categorical data and supports cross-validation or holdout
Best for: Python users and researchers automating PyTorch models for tabular or time-series tasks.
Good for
  • Jointly optimizes architecture and training hyperparameters
  • Supports tabular classification, regression and time-series forecasting
  • Warm-starts search with portfolio and builds ensemble from results
Watch out for
  • Version 0.1.0 breaks compatibility with v0.0.2
  • Forecasting installation requires additional dependencies
  • Current version only supports greedy portfolio

AutoPyTorch at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

AutoPyTorch alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Search & Research

Well-known listings from the same topic.

All 125

AutoPyTorch FAQ

What data does Auto-PyTorch support?
Tabular data for classification and regression, and time series data for forecasting.
How do I install it for forecasting?
Use pip install autoPyTorch[forecasting] to include the additional forecasting dependencies.
Is version 0.1.0 compatible with v0.0.2?
No, moving from v0.0.2 to v0.1.0 breaks compatibility; the old API is available at master_old.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing