Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis

This is the pytorch implement of the paper titled "Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis", the code is inspired by https://github.com/JacobWang95/mWDN and https://github.com/yakouyang/Multilevel_Wavelet_Decomposition_Network_Pytorch. And the dataset is from https://www.cs.ucr.edu/~eamonn/time_series_data_2018/

Noted that the code aims to achieve the task of time series classification(TSF), at the moment it completes the main function which can classify time series from UCR data set. Because the params are not the same as the source code, the classification results differ the paper shows which are better or worse in terms of the data set.