option to occlude all channels simultaneously#3543
Merged
rijobro merged 5 commits intoProject-MONAI:devfrom Jan 13, 2022
Merged
option to occlude all channels simultaneously#3543rijobro merged 5 commits intoProject-MONAI:devfrom
rijobro merged 5 commits intoProject-MONAI:devfrom
Conversation
Signed-off-by: Richard Brown <[email protected]>
1 task
Signed-off-by: Richard Brown <[email protected]>
wyli
approved these changes
Jan 13, 2022
Contributor
|
/build |
Contributor
|
/build |
wyli
pushed a commit
that referenced
this pull request
Jan 14, 2022
* option to occlude all channels simultaneously
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Our current implementation of occlusion sensitivity occludes each channel individually. This PR allows all channels to be occluded simultaneously, which is useful for eg with RGB images, where intuitively it makes sense to block them together.
If
per_channelisTrue(previous implementation, current default for backwards compatibility), the output shape is:B, C, H, W, [D], num_classes.When
per_channelisFalse, output shape is:B, 1, H, W, [D], num_classesmaking it easier to visualise.