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

feat: pass batch size to predict in dynamic deephit #153

Merged
merged 1 commit into from
Mar 22, 2023

Conversation

HLasse
Copy link
Contributor

@HLasse HLasse commented Mar 20, 2023

Description

This PR adds the option to supply a batch_size argument to the predict method of dynamic deephit that will be passed down to predict_survival. This can drastically speed up evaluation.

Affected Dependencies

NA

How has this been tested?

pytest

Checklist

@bcebere
Copy link
Contributor

bcebere commented Mar 20, 2023

Thank you for your contribution!
At the same, I recommend watching this repo https://github.com/vanderschaarlab/temporai
It is dedicated to prediction models, and in the following days it will get a much stable DynamicDeephit variant.

@HLasse
Copy link
Contributor Author

HLasse commented Mar 20, 2023

Fantastic, looking forward to it! Evgeny directed me here for the most up-to-date version of DynamicDeephit while temporai was getting ready. Please let me know when temporai is ready for use, excited to give it a test!

@DrShushen
Copy link
Member

@HLasse a version of temporai with Dynamic DeepHit implementation will be coming end of this week.

@bcebere bcebere requested a review from robsdavis March 21, 2023 09:59
@robsdavis robsdavis merged commit e45ced0 into vanderschaarlab:main Mar 22, 2023
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

Successfully merging this pull request may close these issues.

4 participants