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

Adding integration tests for the JAG MACC models #2004

Merged
merged 9 commits into from
Jan 4, 2022

Conversation

bvanessen
Copy link
Collaborator

Added an integration test for the JAG MACC WAE model to pre-train the
WAE. Moved the MACC model definitions to MACC network architecture
definitions. Created a MACC trainable model function to allow the JAG
application to have a single definition of the trainable WAE model
that is suitable for both application and testing use cases.

python/lbann/util/__init__.py Outdated Show resolved Hide resolved
@bvanessen bvanessen marked this pull request as ready for review November 19, 2021 16:38
WAE.  Moved the MACC model definitions to MACC network architecture
definitions.  Created a MACC trainable model function to allow the JAG
application to have a single definition of the trainable WAE model
that is suitable for both application and testing use cases.
model definition into a separate file for testing.  Renamed the MACC
models file.
@bvanessen bvanessen merged commit 5c8489c into LLNL:develop Jan 4, 2022
@bvanessen bvanessen deleted the add_jag_integration_test branch January 4, 2022 21:00
graham63 pushed a commit to graham63/lbann that referenced this pull request Jan 12, 2022
* Added an integration test for the JAG MACC WAE model to pre-train the
WAE.  Moved the MACC model definitions to MACC network architecture
definitions.  Created a MACC trainable model function to allow the JAG
application to have a single definition of the trainable WAE model
that is suitable for both application and testing use cases.

* Updated the train_macc_surrogate application to have an integrated test.

* Added an integration test for the older JAG model.  Refactored the
model definition into a separate file for testing.  Renamed the MACC
models file.

* Renamed jag_trainable_models to jag_models.

* Removed override of the get_linearized_size in the JAG data reader for
named data fields.

* Tweaked reconstruction ranges for lassen

* Corrected the output cycle loss target values

* Fixed expected run times on pascal

* Fixing up baseline bamboo tests
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