auto-sklearn vs AutoKeras
auto-sklearn
automl.github.ioAutoKeras
autokeras.comSide by side
| Figure | auto-sklearn | AutoKeras |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 2 |
| Spec score · AutoML Software | 7.8 (#12) | 8.9 (#2) |
| Maker | The AutoML website identifies AutoML as a project of the Chair for Machine Learning at the University of Freiburg. | The package is developed by DATA Lab at Texas A&M University with Keras-team collaboration. |
| Security | The opened product documentation describes time and memory resource limits but does not state security certifications or compliance claims. | The official pages opened for this research do not state security certifications or compliance claims. |
| What it does | auto-sklearn automates machine learning model fitting and ensemble construction for classification and regression tasks. | AutoKeras is an AutoML library that automates deep-learning model selection and hyperparameter tuning. |
Plans
In their own words
auto-sklearn
auto-sklearn has no write-up on Specifiction yet; its figures are above.
AutoKeras
AutoKeras is a free, open-source AutoML system based on Keras, designed to make machine learning accessible through code. It supports image and text classification and regression, as well as classification and regression for structured data. Its documentation also includes a tutorial for multi-task or multimodal datasets. Users can assemble custom models from AutoKeras blocks and let the system search for detailed configurations. Image workflows can set architecture type, normalization and data augmentation, or leave those choices for automatic tuning. The best model found can be exported as a Keras Model. The Python package is installed with pip and supports Linux, macOS and Windows, including self-hosted use. The installation guide supports Python 3 and recommends PyTorch version 2.3.0 or later with the PyTorch backend. By default, the final 20% of training data is used for validation, though users can set a different split or supply validation data. Model selection uses validation loss by default, with support for customized metrics and objectives. The project directs users to GitHub Discussions for questions.