The "runner_function.py" is the python script to run experiments with arguments with the following example.

python runner_function.py --framework 'simclr' --backbone 'DCL' --dataset 'ucihar' --aug1 'na' --aug2 'resample' --n_epoch 120 --batch_size 256 --lr 3e-3 --lr_cls 0.03 --cuda 0 --cases 'subject_large' --VAE --tcvae --mean 0.9 --std 0.1

Scripts for training VAE models are mainly taken from "https://github.com/rtqichen/beta-tcvae" 

@inproceedings{NEURIPS2018_1ee3dfcd,
 author = {Chen, Ricky T. Q. and Li, Xuechen and Grosse, Roger B and Duvenaud, David K},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 publisher = {Curran Associates, Inc.},
 title = {Isolating Sources of Disentanglement in Variational Autoencoders},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/1ee3dfcd8a0645a25a35977997223d22-Paper.pdf},
 volume = {31},
 year = {2018}
}

while the structure of contrastive learning comes from "https://github.com/Tian0426/CL-HAR". 

@inproceedings{10.1145/3534678.3539134,
author = {Qian, Hangwei and Tian, Tian and Miao, Chunyan},
title = {What Makes Good Contrastive Learning on Small-Scale Wearable-Based Tasks?},
year = {2022},
isbn = {9781450393850},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3534678.3539134},
doi = {10.1145/3534678.3539134},
booktitle = {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {3761–3771},
numpages = {11},
series = {KDD '22}
}

Both are cited in the paper.

The data_preprocess folder prepares the data for piping into CL setup for training and preprocessing for UCIHAR and HHAR while raw_data_process folder preprocess datasets for USC, Heart rate Prediction and CVD Detection.

