Added the MMD Metric and tests #152
Merged
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
Signed-off-by: Petru-Daniel Tudosiu <petru.daniel@tudosiu.com>
|
Thanks for implementing! I think just the metric is enough for now, Dan. |
|
Ok, then please review it and if you consider it ok merge it. I have also included a transformation which can be seen as applying different kernels to the data such as gaussian or laplace or as in our publications the MedNet3D. |
Warvito
requested changes
Jan 4, 2023
Warvito
approved these changes
Jan 8, 2023
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Outdated suggestions cannot be applied.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.
Added the MMD Metric and required tests.
@Warvito for the tests I tried to create two normal distributions and the MMD metric resulted in a 0.3 value.
I have had a try with the code from torch-two-sample at different alphas bigger than 0 and they also return a non-zero value.
I also had a go at the original code from the alpha WGAN paper and it as well returns a non-zero value.
Given that MMD is a differentiable metric like SSIM should we also implement and test a loss?