Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

all data points will be classified as normal given enough training epochs #13

Open
YingxiaoKong opened this issue Jul 28, 2021 · 6 comments

Comments

@YingxiaoKong
Copy link

Hello,
I tried to implement the LSTM-OCNN on my own dataset, and it seems that the results depends heavily on the number of training epochs: if the training epochs are long enough, all the samples will have same scores and no data point is classified as anomalous. Do you know how to solve this?

@raghavchalapathy
Copy link
Owner

raghavchalapathy commented Jul 28, 2021 via email

@YingxiaoKong
Copy link
Author

Thank you for your quick reply! I have included a LSTM layer as I have time series data, do you also need the data?

@raghavchalapathy
Copy link
Owner

raghavchalapathy commented Jul 28, 2021 via email

@YingxiaoKong
Copy link
Author

https://colab.research.google.com/drive/1c2uhmeZU40L0Pv0VSeTtHRVjvGaM5gVk?usp=sharing

Hello,

here is the link. Unfortunately it's not working on colab. It's working perfectly on my PC. I tried to debug it whole day and still no result. Maybe you could find this out if you're familiar with tensorflow?

The tensorflow on my PC is 2.1.0 and keras is 2.3.1 However these two combinations won't work on colab.

@YingxiaoKong
Copy link
Author

Hi I just debugged it and it's working now!!!!

@yashbhesaniya
Copy link

I was trying to run the code but it shows the error while installing the Fuel library.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants