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

Could you release your trained models #12

Open
navdeepkjohal opened this issue May 2, 2022 · 2 comments
Open

Could you release your trained models #12

navdeepkjohal opened this issue May 2, 2022 · 2 comments

Comments

@navdeepkjohal
Copy link

Hello,

I wish to work RNN-Logic model and do some analysis with it. But unfortunately, I do not have resources to train the RNN-Logic model for FB15K-237 and WN18RR datasets right now. Would it be possible for you to release the trained models (workspace folder and the data/Rules folder) that you obtained while training your model with the optimal hyper-parameters reported in your paper ? That would really help.

@mnqu
Copy link
Collaborator

mnqu commented May 2, 2022

Thanks for your interests in RNNLogic! I am wondering what kinds of data do you need? the trained predictor, trained generator, or the generated logic rules?

@navdeepkjohal
Copy link
Author

Hello,

Thank you for replying back to me! I wish to run test step for 'RNNLogic with embeddings' in line 123-126 in main branch without training the model. And I aim to do it for each relation. Basically, I wish to run the test step of the algorithm 1: for each query use p_{\theta} to generate N rules and feed them to p_{w} for prediction. This would require the optimal trained parameters for both generator and the predictor. Thank you for your consideration.

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