Coder Social home page Coder Social logo

gtn's People

Contributors

huo852yan avatar sqiren avatar sy-ma avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar

Forkers

fan1dy fboeira mpjl jake-00 iju298 vpredictor linkingct oalacam minamisugimura xiaohangguo chenxihe92 fileableswdw elbert-lau sungcheolkim djkim0516 zhouyongxiao brahimharounhassan upcreat paullintilhac 1050ti404 ninja-j wqts xinformatics

gtn's Issues

时间步与维度间编码的方式是不是反了

self.embedding_channel = torch.nn.Linear(d_channel, d_model) #将channel-wise的输入数据映射到d_model维度的线性层。
self.embedding_input = torch.nn.Linear(d_input, d_model) #将step-wise的输入数据映射到d_model维度的线性层
这里分别是对时间步与通道进行编码，而在下边调用时却是，时间步的调用使用的是通道的编码方法，而通道使用的是时间步的编码方法？

step-wise

    # score矩阵为 input， 默认加mask 和 pe
    encoding_1 = self.embedding_channel(x)

channel-wise

    # score矩阵为channel 默认不加mask和pe
    encoding_2 = self.embedding_input(x.transpose(-1, -2))

模型复现问题

作者你好，我下载GTN的代码后，只改动 run.py 文件中数据文件(*.mat)路径和 file_name 变量为常量（‘GTN’），同样用colab的GPU训练模型，拿AUSLAN数据集训练模型测试集最高准确率只有 92.28%，想问下 run.py 里面的超参数是不是最终版？

如何跑自己的2维多元csv数据集

你的论文和代码跑的是多元的3维时间序列，用的是mat文件格式，如果我希望跑的数据集是2维的多元时间序列，用的是csv文件格式如下图，最后一列vs是标签，我该怎么修改代码，可以讲讲大概思路吗？麻烦作者了。
image

模型复现

作者您好，我下载了您的数据集，并按照代码上的超参数跑了三个数据集，但效果都达不到你表格中的结果，请问是否能公开各数据集超参数的表，或者给出训练好的权重文件。

Translation to English

Hello,

Thank you for the great works. Would it be possible to translate the markdown to English? I am trying to translate via the safari translation service but some of the translation is a bit off.

Thank you.

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.