Comments (6)
为什么是合并NC呢?
from stid.
为什么是合并NC呢?
额也许是我对情景理解的不对。我以为N和C基本是同质的,都是channel或feature。比如有N个电表,每个电表有C个字段这样的,所以认为NC应该合并。很多时序问题直接设定的时候就是B,C,L,没有第四个维度。
from stid.
STID主要关注多元时序,N这个维度需要保留以添加Spatial Identity。
from stid.
space embedding本来也是(N,hidden_dim),和(N,C)是类似的吧,都是特征维度的。L应该是length即窗口长度吧,LC合并了,窗口长度变C倍有点诡异。我以为BLNC是指batch,length,node,channel per node的意思。。
from stid.
LC合并到一起并不是为了增大时间窗口。
LC合并到一起,是因为STID只用了一个全连接层做了Encoding,投射到d维度。直接合并LC方便全连接层做计算。
同样,你也可以使用任意的其他网络,比如RNN/TCN把“Channel数为C的N个点"编码成d维的向量。这时候你就不能LC合并了。
from stid.
嗯嗯,明白了,感谢指点:)
from stid.
Related Issues (18)
- Code HOT 1
- 有关于空间Identity HOT 5
- The time series embedding in file "stid_arch.py" HOT 2
- Some questions about the Visualization Section in the paper. HOT 3
- stid_arch.py代码问题 HOT 1
- 关于Spatial and Temporal Identities的问题 HOT 2
- easy-torch和pytorch1.10.0冲突 HOT 1
- Questions about the time of day embedding HOT 3
- 请教一下可视化的代码,能否分享呢?在二维空间中的embedding的可视化的过程 HOT 3
- 请问scaler pkl文件在哪里? HOT 1
- 小白请教是否没有公开模型测试部分的代码 HOT 1
- 请问为什么没有用PEMS03呢?谢谢 HOT 1
- 我感觉预处理完数据后,使用run.py依旧没有办法执行到主函数 HOT 3
- sth about my own dataset HOT 2
- node_emb为什么不和his_data数据交互呢? HOT 4
- How to get prediction with shape [B, L, N, C]
- Question about T^TiD and T^DiW HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stid.