Comments (4)
Hi,
I assume you are displaying the heatmap dimension corresponding to the predicted cluster for each sample. Are the two samples assigned to the same or different clusters?
The heatmap is indicating which region (time steps) of the input contributed most to being assigned to each cluster, so in the first example, the entire time series contributed equally, while in the second, the central part (range 60-110) contributed most.
I suggest also to look at the cluster centroids to interpret the results.
from deeptemporalclustering.
Thanks Florent for your response.
Yes the heatmap dimension is derived using the predicted cluster id for each sample. Both samples are from the same cluster.
I was trying to extract data windows with an event/Anomalous windows using heatmap values ( like if heatmap value breaches above 90% max heatmap value in a cluster ) and loss threshold. Any suggestion on this?
I will look into the cluster centroids .
from deeptemporalclustering.
How can i generate a heatmap or heatmaps ?
from deeptemporalclustering.
@JJQKA2, see for instance this issue
from deeptemporalclustering.
Related Issues (20)
- Dimension Reduction HOT 7
- Assertion error HOT 5
- Heatmap HOT 3
- Nan: Predicted Value HOT 2
- ValueError: The name "reshape" is used 2 times in the model. All layer names should be unique. HOT 3
- CuDNNLSTM not found HOT 3
- Training and Validation Losses HOT 1
- ValueError: Input 0 is incompatible with layer AE: expected shape=(None, 5210, 6), found shape=(None, 6) HOT 3
- Problem with Autoencoder Dimensions HOT 2
- Heatmap use HOT 2
- input shape HOT 2
- how to load model.h5 HOT 2
- About the loss value HOT 2
- Loss interpretation
- Agglomerative Clustering without n_clusters HOT 1
- Dependency Problems with cudnn and Tensorflow HOT 1
- Practical Use
- Requirements are hard to find out HOT 1
- variable time step HOT 4
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 deeptemporalclustering.