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

Keras3 update #39

Merged
merged 5 commits into from
May 8, 2024
Merged

Keras3 update #39

merged 5 commits into from
May 8, 2024

Conversation

charlie-becker
Copy link
Collaborator

The main updates in this PR now use models trained with the updated miles-guess evidential models (subclassed with keras 3 models). They are simply loaded with keras.models.load_model() and no longer depend on a training configuration file.

Other additions:

  • Began implementing support for the GEFS ensemble, but is not quite complete.

Copy link
Collaborator

@djgagne djgagne left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The changes all generally look like a good improvement and better integration with miles-guess and bridgescaler. I only have one comment regarding some hard coded settings that should be easy to address.


x_data = transform_data(input_data=data,
transformer=transformer,
input_features=input_features)

if config["evidential"]:
predictions = model.predict_uncertainty(x_data)
predictions = model.predict(x_data, return_uncertainties=True, batch_size=2048)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you make return_uncertainties and batch_size config options rather than be hard coded?

@charlie-becker
Copy link
Collaborator Author

Thanks for the review -- resolved.

@charlie-becker charlie-becker merged commit 4d8a66c into main May 8, 2024
1 check passed
@charlie-becker charlie-becker deleted the keras3_update branch May 8, 2024 14:47
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.

2 participants