Add ResolutionInvariantReadout with FNO integration and gallery examples#719
Open
JoshBeacom wants to merge 1 commit intoneuraloperator:mainfrom
Open
Add ResolutionInvariantReadout with FNO integration and gallery examples#719JoshBeacom wants to merge 1 commit intoneuraloperator:mainfrom
JoshBeacom wants to merge 1 commit intoneuraloperator:mainfrom
Conversation
- ResolutionInvariantReadout maps field outputs to scalar QoIs via spatial reduction (mean/integral) and a linear/MLP projection head - Integrated as optional readout parameter on FNO with in_channels validation; OTNO guards against readout use due to incompatible output shape - Two gallery examples: Darcy scalar QoI and 3-D Poisson-Boltzmann screened energy demonstrating resolution invariance
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
ResolutionInvariantReadout, which maps FNO field outputs(B, C, *spatial)to scalar or vector quantities of interest(B, out_dim)via spatial pooling (meanor physical integral) and a linear or MLP head.FNO integration
readoutparameter toFNOreadout.in_channels == out_channels;complex_data=Trueis rejected)OTNOrejectsreadoutbecause its output shape is incompatibleGallery examples
32x32after training at16x16reduce="integral"with a physical domain measure and evaluates the same latent test systems at16^3and24^3to demonstrate resolution invariance directlyTests
Tests cover output shapes, gradients, measure scaling, constructor/forward validation, and OTNO rejection of incompatible readouts.