aai-institute / continuiti

Learning function operators with neural networks.

GNU Lesser General Public License v3.0

20 stars 3 forks source link

Make Trainer usable with standard torch model. #114

Closed samuelburbulla closed 6 months ago

samuelburbulla commented 6 months ago

Feature: Make Trainer usable with standard torch model.

Description

Which issue does this PR tackle?

Trainer is a general training loop implementation, but does not work with standard torch models.

How does it solve the problem?

Adapts only a few lines in Trainer.fit such that we can also train torch models with it.
Fixes the PrintTrainingLoss to print the current test loss (which is also used for stopping criterion).

How are the changes tested?

Added test_trainer_with_torch_model.

Checklist for Contributors

[x] Scope: This PR tackles exactly one problem.
[x] Conventions: The branch follows the feature/title-slug convention.
[x] Conventions: The PR title follows the Bugfix: Title convention.
[x] Coding style: The code passes all pre-commit hooks.
[x] Documentation: All changes are well-documented.
[x] Tests: New features are tested and all tests pass successfully.
[x] Changelog: Updated CHANGELOG.md for new features or breaking changes.
[x] Review: A suitable reviewer has been assigned.

Checklist for Reviewers:

[x] The PR solves the issue it claims to solve and only this one.
[x] Changes are tested sufficiently and all tests pass.
[x] Documentation is complete and well-written.
[x] Changelog has been updated, if necessary.