WaveDiff: New PSF Model Features, Refactoring, Rotation Obscuration Mask, and PEP8 Compliance#142
Merged
jeipollack merged 449 commits intodevelopfrom Aug 5, 2025
Merged
Conversation
…for ground truth models
…sf_model method and add iteration over metrics evaluation functions
…ricField to psf model registry
Member
|
The last commits include a general script to simulate datasets that contain all the currently supported scenarios and should integrate all the previously created datasets (Closes #160 ) |
…ton causing non-deterministic results
The DataHandler compared `self.dataset_type` to "train", so the conversion of `noisy_stars` to `tf.float32` was skipped for the training split. This silent mismatch left the array in a different dtype than the rest of the pipeline and, over multiple epochs, caused the validation-loss divergence seen between the old and refactored branches. - Change comparison to `self.dataset_type == "training"`. - Keep the explicit `elif self.dataset_type == "test"` for clarity. With the correct split name, preprocessing is identical across branches and metrics are now fully reproducible.
…tances each training cycle Fixes a bug where metric objects retained state across training cycles, leading to incorrect metric calculations and premature convergence. By creating fresh loss and metric instances per cycle, internal states are reset properly, ensuring consistent training behavior.
jeipollack
changed the title
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR includes new features:
pyproject.toml(Closes Failure of Black Test in CI testing in github #119, Fix black test failure in CI #120,CI Failure: Black Formatting & TensorFlow Import Error #145)pyproject.toml(Closes Bug: CI fails with pytest 8.1.dev #125)train_utils.pywith helper functions and removes unused code (Closes Refactor train_utils module #89 and Computing Sample Weights: Hardcoding of strategy_opt=1 and strategy_opt=0 Issues #152)test_trainingdirectory with unit tests fortrain.pyandtrain_utils.pymodulestrain_utils.pyandtrain.pymodules using Strategy Pattern