Yong Liu
Thanks for your concern, you can find the exact requirements version in this repository: https://github.com/thuml/Koopa.
很高兴iTransformer作为深度模型应用于业务系统，方便的话能否提供若干场景细节，例如预测任务，特征属性等
We tested itransformer on the classification task with [tslib](https://github.com/thuml/Time-Series-Library), but it seems alternative models can be a good choice. We implement it by **averaging** the variate tokens. However, introducing learnable...
Of course, we are in process now! You may be interested in our recent work where iTransformer is further enhanced with covariates for time series forecasting! [TimeXer: Empowering Transformers for...
大家好，因为文章投稿的问题，TimeXer的代码还没有开源，后续开源后会尽快通知感兴趣的朋友们
大家好！TimeXer将在这个仓库开源：https://github.com/thuml/TimeXer
Hello! Please refer to this: https://github.com/thuml/iTransformer/issues/44
Hi, please take a look at [the relevant issue](https://github.com/thuml/iTransformer/issues/19)
Hi, since multivariate forecasting has the intrinsic problem of mixture frequency, it is better to regard each variate independently like iTransformer and use different embedding layers for varied variates if...
> label_len,是根据什么定义的呢？ please refer to https://github.com/zhouhaoyi/Informer2020