RapidAE

Python library for creating, experimenting with, and benchmarking autoencoders

Autoencoders have proven successful across diverse applications such as data reconstruction, anomaly detection, and feature extraction, however, these advancements remain largely dispersed among various fields, lacking a cohesive tool that unifies them. Rapidae is an open-source Python library created to facilitate the use, development, and benchmarking of autoencoder models. Through a simple environment, it is suitable for educational purposes yet flexible to meet research needs. Rapidae is mainly oriented to image and time-series research, in the form of precise and imprecise data and is designed to be backend-agnostic, supporting a seamless transition between TensorFlow, PyTorch, and JAX, thus accommodating a broad range of user preferences and existing workflows. In addition to its computational flexibility, Rapidae offers a graphical user interface, which lowers the barrier to entry for new learners and enhances the productivity of seasoned practitioners.