Comments (4)
Is it unsupervised learning?
Yes. The network in this repo is trained as a non-supervised learning method. Labels are not used when training.
Why is the label needed?
Labels are needed to evaluate model performance. If there is no label, how can we evaluate the accuracy of the model?
I think the train data does not contain anomalies and the test data contains anomalies. So, I process my data as follow, the train data is the normal historical data while the test data contains man-made anomalies, but the result is disappointing. What can I do?
What does your data look like? Is the data periodic? I think the method seems hard to detect anomalies of aperiodic data.
from rnn-time-series-anomaly-detection.
As the picture above, the data is periodic. I do not know which data should be labeled 1 and which data should be labeled 0 as my train data has no anomaly while the test data contains anomalies, and they are collected respectively in different situation as follow:
@chickenbestlover
from rnn-time-series-anomaly-detection.
Wow, your data looks really cool! I never tried 16-dimensional data simply because I don't have one.
I cannot find any anomalous points in your data. Is this figure test dataset which contains anomalous points? If so, where are anomalous points?
And from which sensor did you get the last anomaly scores?
from rnn-time-series-anomaly-detection.
As the picture above, the data is periodic. I do not know which data should be labeled 1 and which data should be labeled 0 as my train data has no anomaly while the test data contains anomalies, and they are collected respectively in different situation as follow:
@chickenbestlover
Can it be real-time monitoring?
from rnn-time-series-anomaly-detection.
Related Issues (20)
- loss function
- [BUG]: Model saving logic is wrong HOT 1
- [BUG]: Computing normal stats is wrong
- UnicodeDecodeError on Windows10 HOT 3
- RuntimeError: view size is not compatible with input tensor's size and stride HOT 2
- Training on Custom Dataset
- Operation does not have an identity.
- What if you have taxi data from multiple states?
- repackage_hidden의 역할이 뭔가요? HOT 1
- The program is stuck when running SRU, there is no prompt message
- error changes HOT 1
- Runtime error running example HOT 3
- resume problem
- RuntimeError when using tie_weights=True
- Labels of the datasets HOT 1
- paper
- 调通代码
- what data augmentation method you use?
- A question about the size of the rnn input emb in function forward HOT 1
- `chfdb_chf14_45590.pkl` file isn't found
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 rnn-time-series-anomaly-detection.