LAUSR

Objective. In recent years, deep learning has blossomed in the field of electrocardiography (ECG) processing, outperforming traditional signal processing methods in a number of typical tasks; for example, classification, QRS detection and wave delineation. Although many neural architectures have been proposed in the literature, there is a lack of systematic studies and open-source libraries for ECG deep learning. Approach. In this paper, we propose a deep learning package, named torch_ecg, which assembles a large number of neural networks, from existing and novel literature, for various ECG processing tasks. The models are designed to be able to be automatically built from configuration files that contain a large set of configurable hyperparameters, making it convenient to scale the networks and perform neural architecture searching. torch_ecg has well-organized data processing modules, which contain utilities for data downloading, visualization, preprocessing and augmentation. To make the whole system more user-friendly, a series of helper modules are implemented, including model trainers, metric computation and loggers. Main results. torch_ecg establishes a convenient and modular way for automatic building and flexible scaling of networks, as well as a neat and uniform way of organizing the preprocessing procedures and augmentation techniques for preparing the input data for the models. In addition, torch_ecg provides benchmark studies using the latest databases, illustrating the principles and pipelines for solving ECG processing tasks and reproducing results from the literature. Significance. torch_ecg offers the ECG research community a powerful tool for meeting the growing demand for the application of deep learning techniques. The code is available at https://github.com/DeepPSP/torch_ecg.