AutoGluon vs AutoKeras

AutoGluon is a free, open-source Python library for automating machine learning across tabular, time-series, and multimodal data. For tables, it trains classification and regression models while handling data cleaning, feature engineering, hyperparameter optimization, and model selection. Its TimeSeriesPredictor produces probabilistic forecasts for multiple time series using historical data and related covariates. AutoMM reduces manual work in adapting foundation models to specialized data. Documentation examples cover image and text prediction, object detection, image segmentation, document prediction, entity extraction, and semantic matching. AutoMM can adapt models from Hugging Face, TIMM, and MMDetection collections. Forecasting methods include ETS and ARIMA from StatsForecast, LightGBM, DeepAR and Temporal Fusion Transformer from GluonTS, and Chronos. AutoGluon supports Python 3.10 through 3.13 on Linux, macOS, and Windows. GPU usage is not supported on macOS; the installation guide points GPU users to Linux or Windows. AutoGluon is licensed under Apache 2.0. Cloud options include AutoGluon Cloud, described as a free wrapper, and Amazon SageMaker, where compute and S3 storage are billed to the user’s AWS account.

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.