Feature/kedro 1.0#45
Open
dermatologist wants to merge 9 commits into
Open
Conversation
There was a problem hiding this comment.
Pull Request Overview
This pull request upgrades a Kedro project from version 0.18.x to Kedro 1.0, modernizing the codebase structure and dependencies. The upgrade involves significant changes to align with Kedro's new patterns and conventions.
- Upgrades to Kedro 1.0 with new session-based architecture and OmegaConfigLoader
- Updates TensorFlow/Keras imports to use standalone keras package instead of tensorflow.keras
- Modernizes dataset classes with new AbstractVersionedDataset base class and type annotations
Reviewed Changes
Copilot reviewed 54 out of 64 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/test_run.py | Completely new test file with updated Kedro session API and modernized test patterns |
| tests/pipelines/preprocess/test_pipeline.py | Updated test structure removing deprecated KedroContext pattern |
| src/kedro_tf_image/settings.py | Migrated to Kedro 1.0 settings format with OmegaConfigLoader |
| src/kedro_tf_image/pipelines/preprocess/nodes.py | Updated keras imports and improved type annotations |
| src/kedro_tf_image/extras/datasets/*.py | Modernized dataset classes with new base classes and type hints |
| pyproject.toml | Complete project configuration overhaul for Kedro 1.0 |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Comment on lines
+38
to
+39
| tf.TensorSpec(shape=(None, imagedim, imagedim, 3), dtype=tf.float32, name=None), # type: ignore | ||
| tf.TensorSpec(shape=(None,), dtype=tf.int32, name=None), # type: ignore |
There was a problem hiding this comment.
[nitpick] The # type: ignore comments suggest type checking issues. Consider addressing the underlying type issues rather than ignoring them, or add more specific type ignore codes.
Suggested change
| tf.TensorSpec(shape=(None, imagedim, imagedim, 3), dtype=tf.float32, name=None), # type: ignore | |
| tf.TensorSpec(shape=(None,), dtype=tf.int32, name=None), # type: ignore | |
| tf.TensorSpec(shape=cast(tuple[int | None, ...], (None, imagedim, imagedim, 3)), dtype=tf.float32, name=None), | |
| tf.TensorSpec(shape=cast(tuple[int | None, ...], (None,)), dtype=tf.int32, name=None), |
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
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.
No description provided.