Giter Site home page Giter Site logo

数据集泛化问题 about step HOT 5 CLOSED

fuyuyuputao avatar fuyuyuputao commented on May 23, 2024
数据集泛化问题

from step.

Comments (5)

zezhishao avatar zezhishao commented on May 23, 2024 1

没有遇到过,STEP在METR-LA、PeMS-BAY、PeMS03、PeMS04、PeMS07、PeMS08上都做过实验,看起来一切正常。

from step.

fuyuyuputao avatar fuyuyuputao commented on May 23, 2024

您好,我根据您提供的数据预处理代码生成了训练数据,在METR-LA、PeMS-BAY都能够看到和您提供的训练日志几乎一样的结果,我换了个数据集后发现损失值很大且很难下降。数据集是下面这个电力的数据集:
https://archive.ics.uci.edu/ml/datasets/ElectricityLoadDiagrams20112014
然后由于数据集太大,我进行了降采样:
https://drive.google.com/file/d/1SAcq-cHZqhnwPL5gjm6yo6dMbW_ec2Rn/view?usp=share_link
我使用您提出的预训练tsformer模型预训练降采样后的数据集,发现训练损失很大,是我超参数设置的不合理嘛?

from step.

fuyuyuputao avatar fuyuyuputao commented on May 23, 2024

非常感谢您的回复

from step.

zezhishao avatar zezhishao commented on May 23, 2024

抱歉,我没有在ETT上做过实验,无法给您具体的解答,只能给您一些模糊的见解。

一方面,ETT数据集的采样频率、取值范围、异常值数据等和我提到的数据集完全不同,建议您检查数据预处理是不是正确,得到的格式是否符合STEP的要求。

另一方面,ETT数据集的特点是没有明显的模式、分布飘逸特别严重、噪声较大。不太建议您在上面做研究,很难得到可靠的结论。考虑到其模式不明确、噪声大,所以模型结构越复杂,效果越差。您可以考虑使用我的另一个仓库中的STID模型,可以直接打败一众Transformer模型和Linear模型。但总的来说,个人感觉ETT数据集不太适合做科研,真想刷榜,使用一些工程化的方法(多采样、层次化、集成学习等)效果更加显著。

from step.

fuyuyuputao avatar fuyuyuputao commented on May 23, 2024

感谢大佬。

from step.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.