TODOs & HOWTOs - Githubissues

zezhishao / BasicTS

A Standard and Fair Time Series Forecasting Benchmark and Toolkit.

Apache License 2.0

468 stars 84 forks source link

TODOs & HOWTOs #95

Open zezhishao opened 7 months ago

zezhishao commented 7 months ago

How-Tos

[ ] How to add new datasets.
[ ] How to config the config file.
[ ] How to inference and save the inference results.
[ ] How to customize loss function.

ToDos

Add more baselines:

[x] Add DeepAR
[x] Add LightGBM
[x] Add NHiTS
[x] Add GRU
[x] Add STGODE
[x] Add SCINet
[x] Add STSGCN❌, STFGCN❌ (They are built on MXNet)
[x] Add TimesNet
[ ] Add Vanilla Transformer
[x] Add GPTs for Time Series
[ ] Add AMP.
[ ] Add early stopping.

Add more datasets:

[x] Add M4 dataset
[ ] Add PeMSD7(M) and PeMSD7(L).

Others:

[ ] Unify the data preprocssing script.
[ ] Support lr scheduler ReduceLROnPlateau. (see #120 )
[x] Fix issue #90 .
[ ] Add AutoML.

huangst21 commented 7 months ago

您好，感谢您提供的框架。关于交通预测问题，或许您可以考虑添加上PEMS07(M)和PEMS07(L)这两个数据集？

zezhishao commented 7 months ago

您好，感谢您提供的框架。关于交通预测问题，或许您可以考虑添加上PEMS07(M)和PEMS07(L)这两个数据集？

Of course, could you provide me the source of these two datasets? E.g., links or papers.

huangst21 commented 7 months ago

您好，感谢您提供的框架。关于交通预测问题，或许您可以考虑添加上PEMS07(M)和PEMS07(L)这两个数据集？

Of course, could you provide me the source of these two datasets? E.g., links or papers.

STGCN的库里包含了这两个速度数据集： https://github.com/VeritasYin/STGCN_IJCAI-18

zezhishao commented 5 months ago

@all-contributors please add @zezhishao for maintenance,infra,code,bug. please add @LMissher for code,bug. please add @cnstark for infra. please add @Azusa-Yuan for bug. please add @ywoelker for bug. please add @hlhang9527 for bug.

littleheuer commented 3 months ago

How to set AMP?

zezhishao commented 3 months ago

How to set AMP?

Currently, BasicTS does not support AMP because these baselines don’t have many parameters. However, I have also recently tested AMP in BasicTS to facilitate training and inference of large time series models. AMP will be added in the future (probably next version).

If you are want to use AMP, you need to init torch.amp.autocast and torch.cuda.amp.GradScaler in the __init__ function of the runner, and then modify the train_iters, val_iters, test, and backward function.