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

DNN-LSTM problem #24

Closed
jycccccccc opened this issue May 26, 2020 · 2 comments
Closed

DNN-LSTM problem #24

jycccccccc opened this issue May 26, 2020 · 2 comments

Comments

@jycccccccc
Copy link

Thanks for the paper and your job.
I have a question about the DNN-LSTM structure. You said in the paper that you stacked LSTM design will capture the temporal information and outperform DNN-only setting. But what I see from the code is that you shuffle the data in the provider file, which means the temporal information is lost. Also I didn't see you feed time sequence data into the network. It makes me confused. So I want to know how your cnn_lstm_block works exactly.
Hope for reply. Thanks.

@wangjksjtu
Copy link
Contributor

Thanks for the interest in our work! Yes, you should disable the shuffling line when you use the DNN-LSTM structure.

Note that we only release the code for DNN-only in this repo (see README.md). The cnn_lstm_block is just for reference. It is neither tested nor cleaned in this repo.

@jycccccccc
Copy link
Author

Thanks a lot!

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

2 participants