-
Notifications
You must be signed in to change notification settings - Fork 317
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
2 Layer LSTM #20
Comments
Sorry to confuse you. I used only the part to calculate the anomaly score
of the paper.
2018년 12월 31일 (월) 오전 1:36, Tobias128128 <[email protected]>님이 작성:
… In the article "LSTM-based Encoder-Decoder for Multi-sensor Anomaly
Detection" from Malhotra are two LSTM layers (encoder and decoder)
mentioned. You refered to that article and you wanted to implement that
concept. But I can't see in your RNNPredictor-model that you implement two
separate LSTM layer. Do you deviate from that concept intentionally or have
I missed something?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#20>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AJ2X1DmbCmM-vBPOOc1nWHpeUn2zqII4ks5u-Ot2gaJpZM4Zk_sg>
.
|
Thank you for your response. |
You mean enc-dec model is better than rnn prediction model? Yes, I assume
that it is because 'reconstruction' is easier than 'prediction'.
2018년 12월 31일 (월) 오후 10:37, Tobias128128 <[email protected]>님이 작성:
… Thank you for your response.
Do you think that the architecture in this paper from Malhotra is more
powerful?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#20 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AJ2X1EWnIhnfuxieeLWeag42gEjHvVHFks5u-hMdgaJpZM4Zk_sg>
.
|
I‘ve implemented the lstm autoencoder model in pytorch and it seems to work great with machine data. I‘m now validating the model... |
I have read the article 'LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection'. |
Did you use a Sequence2Sequence like model for this? |
In the article "LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection" from Malhotra are two LSTM layers (encoder and decoder) mentioned. You refered to that article and you wanted to implement that concept. But I can't see in your RNNPredictor-model that you implement two separate LSTM layer. Do you deviate from that concept intentionally or have I missed something?
The text was updated successfully, but these errors were encountered: