Bug fix for explainer attributes visalization #12
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
kamilrzechowski
requested review from
adamjankaczmarek,
rpytel1 and
adamwawrzynski
adamwawrzynski
pushed a commit
that referenced
this pull request
Dec 28, 2022
Signed-off-by: Adam Wawrzyński <adam.wawrzynski@reasonfieldlab.com>
adamwawrzynski
added a commit
that referenced
this pull request
Dec 28, 2022
* Change kwargs argument name, unify 'layer' argument name passed to explainers * Fix docstrings of create_explainer function * Add Saliency algorithm * Add DeepLIFT algorithm * Add DeepLIFT SHAP algorithm * Add Deconvolution algorithm * Add Input x Gradient algorithm * Add Layer Conductance algorithm * Add standardization of matrices, generate figure with respect to presence of negative attributions * Revert visualization error handling due to #12 PR * Mark model argument type with TODO * Remove incorrect standardization method * Bump patch version
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Outdated suggestions cannot be applied.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
Captum visualization method
captum.attr.visualization.visualize_image_attr_multipleallows us to visualize positive, negative, and both attributes together. Sometimes, however, the input image doesn't have negative or positive attributes contributing to the model output. In such a case captum visualization tool throws an error. The given PR introduces a fix, which checks the explainer attributes for the presents of positive and negative attributes and requests only attributes, that are present.Additionally, the PR adds the logger creation function.
Checklist:
pyproject.tomlfiles.