PhysioEx ( Physiological Signal Explainer ) is a versatile python library tailored for building, training, and explaining deep learning models for physiological signal analysis.
The main purpose of the library is to propose a standard and fast methodology to train and evalutate state-of-the-art deep learning architectures for physiological signal analysis, to shift the attention from the architecture building task to the explainability task.
With PhysioEx you can simulate a state-of-the-art experiment just running the train
command; evaluating and saving the trained model; and start focusing on the explainability task! The train
command will also take charge of downloading and processing the specified dataset if unavailable.
- Chambon2018 model for sleep stage classification.
- TinySleepNet model for sleep stage classification.
- SeqSleepNet model for sleep stage classification (time-frequency images as input).
- SeqECGnet model for ECG arrythmia classifiaction ( 5-AAMI classes ).
- SleepEDF (version 2018-2013) sleep staging dataset.
- Dreem (version DODO-DODH) sleep staging dataset.
- MIT-BIH Arrhythmia Database dataset for ECG analysis.
- Clone the Repository:
git clone https://github.com/guidogagl/physioex.git
cd physioex
- Create a Virtual Environment (Optional but Recommended)
conda create -n physioex python==3.10
conda activate physioex
conda install pip
pip install --upgrade pip # On Windows, use `venv\Scripts\activate`
- Install Dependencies and Package in Development Mode
pip install -e .
- adding a download_pretrained command to let users automatically download pretrained models on the supported datasets
- adding support for https://github.com/mkdocstrings/mkdocstrings?tab=readme-ov-file