Next step in handling Cloud AI attributions in WIT #2316
Conversation
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 Outdated suggestions cannot be applied.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.
Working towards visualizing attributions if they are returned from Cloud AI models along with predictions.
Allow optional setting of signature_name to pass to Cloud AI model for prediction. Previously we only allowed using the default serving signature, but we should support this parameter as well.
For models that take lists of feature values and feature name maps, correctly map attributions to those feature names so they can be displayed correctly by WIT.
When attributions contain a list of attribution objects, for now WIT only displays the first set of attributions, meaning for the top class returned. In later PRs we will enhance this logic.
Test locally-built pip package with multiple cloud models that return attributions and ensure that attributions are correctly shown by WIT.