Fix memory overflow and Expand model validation #33
Conversation
This file contains 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
Contributor
6Naci
commented
Jul 4, 2023
6Naci
commented
- Removing unnecessary computational graph when using the cache
- General conformity check (of the last layer) for the cache_model
|
Ну можно вливать, получается. @nikiniki1 не забудь сделать ребейз, на этот PR, когда доделаешь примеры. This RP serves for performance fixes concerning excessive computational graph saving and work with cache when output layer is not linear. |
SuperSashka
approved these changes
Jul 5, 2023
nikiniki1
added a commit
that referenced
this pull request
Jul 26, 2023
* Refactor + adaptive lambdas Currently adaptive lambdas are not working due to pytorch features. * Update lambdas Now adaptive lambdas are working * Update docstrings * Some fixes + new example - Fix for output for Fourier features - Adaptive lambdas now work for systems - 1D Navier-Stokes example * Fix for examples Small fixes for examples and docstrings * Compatibility fix * Solution initialization fix for mat * LV img save fix * Fix memory overflow and Expand model validation (#33) * Fix memory overflow and Expand model validation * Version update for actions --------- Co-authored-by: Titov Roman <r.titov@itmo.ru> Co-authored-by: SuperSashka <heretik.unlimited@gmail.com> * Updated lambdas NTK -> sensitivity analysis * Update derivative.py Docstrings update * Some fixes + docstrings Updated project structure. - new modules ('eval' for evaluating operator and boundaries, 'losses' for all losses). Minor improvements due to new improvements. * Refactor + adaptive lambdas Currently adaptive lambdas are not working due to pytorch features. * Update lambdas Now adaptive lambdas are working * Update docstrings * Some fixes + new example - Fix for output for Fourier features - Adaptive lambdas now work for systems - 1D Navier-Stokes example * Fix for examples Small fixes for examples and docstrings * Compatibility fix * Solution initialization fix for mat * LV img save fix * Updated lambdas NTK -> sensitivity analysis * Some fixes + docstrings Updated project structure. - new modules ('eval' for evaluating operator and boundaries, 'losses' for all losses). Minor improvements due to new improvements. * Cache fix for lambdas * Small fixes * Cache fix * Normalized loss Added normalized loss as stop criterion * loss -> normalized_loss in cache, small exp fix * Experiment fix * example rework * Cache fix Fixed a bug with the same loss when using the cache * Small cache fix * More predictable cache directory * Example fix * Clear cache functionality --------- Co-authored-by: SuperSashka <heretik.unlimited@gmail.com> Co-authored-by: Roman Titov <47646069+6Naci@users.noreply.github.com> Co-authored-by: Titov Roman <r.titov@itmo.ru>
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.