Fix adaptive refinement #571
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FilippoOlivo
added
enhancement
FilippoOlivo
force-pushed
the
refinement
branch
4 times, most recently
from
5e9ccc6 to
ca57ef0
Compare
|
Code Coverage SummaryResults for commit: 2a316a8 Minimum allowed coverage is ♻️ This comment has been updated with latest results |
There was a problem hiding this comment.
Pull Request Overview
This PR fixes issue #539 by refactoring the adaptive refinement functionality and updating the related tests and documentation. Key changes include the migration of the R3Refinement callback to a new module structure, the removal of the deprecated adaptive_refinement_callback, and an addition of a dataset update method to support the new refinement logic.
Reviewed Changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/test_callback/test_adaptive_refinement_callback.py | Updated imports and test functions for the new R3Refinement callback, including a keyword change from "callback" to "callbacks". |
| pina/data/dataset.py | Added update_data() method to enable dataset updates with new conditions. |
| pina/callback/refinement/refinement_interface.py | Introduced the new refinement interface with adaptive point updating logic. |
| pina/callback/refinement/r3_refinement.py | Implemented the R3Refinement callback for adaptive point sampling. |
| pina/callback/adaptive_refinement_callback.py | Removed the deprecated adaptive refinement callback implementation. |
| pina/callback/init.py | Updated callback exports to reflect the new module structure. |
| docs | Revised documentation to reference updated module paths for refinement callbacks. |
|
@dario-coscia I fixed codacy warnings in your code! Let me know if the changes are ok! |
Great! Code-wise and test, I think we are ready to go. Would you mind adjusting the docstrings ? |
|
@dario-coscia Done! |
dario-coscia
approved these changes
May 14, 2025
dario-coscia
added
pr-to-review
|
For me is good to go, @GiovanniCanali what do you think? |
GiovanniCanali
requested changes
May 15, 2025
pina/data/dataset.py
Outdated
| parameter. | ||
|
|
||
| :param dict new_conditions_dict: Dictionary containing the new data. | ||
| :type new_conditions_dict: dict |
There was a problem hiding this comment.
Please, remove :type new_conditions_dict: dict, as type is already specified in the previous line.
| :param ~lightning.pytorch.trainer.trainer.Trainer: The trainer object. | ||
| :param PINNInterface solver: The solver object. | ||
| """ | ||
| if trainer.current_epoch % self.sample_every == 0: |
There was a problem hiding this comment.
I would modify this control as follows:
if (trainer.current_epoch % self.sample_every == 0) and (trainer.current_epoch != 0)This is done to avoid resampling after the first epoch.
| :param solver: The solver object. | ||
| :return: New points sampled based on the R3 strategy. | ||
| :rtype: LabelTensor | ||
| """ |
There was a problem hiding this comment.
Please, add parameters' type to this docstring.
GiovanniCanali
approved these changes
May 16, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR fixes #539
Checklist