#37 · Primary category: MLOps & Evaluation

autogluon

autogluon automated-machine-learning automl computer-vision data-science deep-learning ensemble-learning forecasting gluon hyperparameter-optimization machine-learning natural-language-processing object-detection python pytorch scikit-learn structured-data tabular-data time-series transfer-learning

Fast and Accurate ML in 3 Lines of Code

Project last updated:08/28/26

GitHub Stars

10.6K

Forks

1.2K

Contributors

166

License

Apache-2.0

Why we included this project

AutoGluon, built by AWS AI, is an AutoML library that removes the chore of assembling a model stack yourself. You pass it tabular, time-series, or multimodal data and it runs the model search and hyperparameter tuning, then blends the best candidates into an ensemble and hands back a predictor you can call directly. The tabular path is especially strong for structured business data, and the time-series and multimodal predictors carry the same hands-off approach into forecasting and mixed text-plus-image inputs. Since it's a full Python library with thorough documentation, it drops into existing pipelines, supports GPU training and export for serving, and gives you a defensible baseline before you invest in bespoke modeling. Data scientists and engineers who want reliable AutoML without locking themselves out of the internals will find a practical middle ground.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category