Fixed "ValueError" in epsilon_schedule() when computing 0 sinkhorn distance. #77
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
… Maximum allowed size exceeded" in epsilon_schedule() caused by np.log(0).
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Outdated suggestions cannot be applied.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.
fixed #34, #51, #74.
Cause
The roughly estimated maximum diameter is 0. By default, diameter of
geomloss.SamplesLossisNone, an upper bound of the distance will be roughly estimated and used for generating the epsilon list. When the inputs are too close or the same, the estimated maximum diameter could be 0. Thenp * np.log(diameter)*raises ValueError: Maximum allowed size exceeded for np.log(0) is -inf.Solution
Set the argument blur as a lower bound for diameter. This still provides a valid eps_list for the further process.
Results
Using the case in #51
