| Data/
|————work condition1.xx
|----work condition2.xx
|----.....

--optimizer_name: str, The optimizer which is supported in training processing, if you want to add or define new optimzier, please update the create_optimizer function
--lr_scheduler: str, The learning rate scheduler which is supported in training processing, if you want to add or define new scheduler, please update the create_scheduler function
--loss_name: str, The loss function which is supported in training processing, if you want to add or define new loss, please update the create_loss function
--datasets: str, The way which is supported to load datasets
--model_name: str, the model in repository
--use_ratio: bool, whether to use ratio to divide datasets in traning and testing samples
--size: The total number of samples in each category. It works only the use_ratio is set as True
--train_size_use: The number of training samples of each category. It works only the use_ratio is set as False
--test_size:The number of training samples of each category. It works only the use_ratio is set as False
--num_cls: The number of categories
-ic, --input_channel: The channel of the input data
--layer_args: The structure and parameters of classifier

python train.py --work_dir to/path/data --model vgg11 --datasets hnu_datasets --num_cls 8

python train.py --work_dir to/path/data --model max_vit_tiny_16 --datasets hnu_datasets --length 1024 --num_cls 8

@article{Han2022DL,
        title={Novel multi-scale dilated CNN-LSTM for fault diagnosis of planetary gearbox with unbalanced samples under noisy environment},
        author={Han Songyu and Zhong Xiang and Shao Haidong and Xu Tianao and Zhao Rongding and Cheng Junsheng},
        journal={Measurement Science and Techonology},
        year={2021}}

@article{Han2022DL,
        title={Convformer-NSE: A Novel End-to-End Gearbox Fault Diagnosis Framework Under Heavy Noise
Using Joint Global and Local Information},
        author={Han Songyu and Shao Haidong and Cheng Junsheng and Yang Xingkai and Cai Baoping},
        journal={IEEE/ASME Transactions on Mechatronics},
        year={2022}}

@article{Han2022DL,
        title={End-to-end chiller fault diagnosis using fused attention mechanism and dynamic cross-entropy under imbalanced datasets},
        author={Han SongYu and Shao Haidong and Huo Zhiqiang and Yang Xingkai and Cheng Junsheng},
        journal={Building and Environment},
        year=2022}}

[1] Tianfu Li, Zheng Zhou, Sinan Li, Chuang Sun, Ruqiang Yan, Xuefeng Chen, “The emerging graph 
neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study,”
*Mechanical Systems and Signal Processing*, vol. 168, pp. 108653, 2022. DOI:
10.1016/j.ymssp.2021.108653