Fix downscaling and data type of segmentation masks #29
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
uermel
changed the title
…el of the pyramid.
manasaV3
reviewed
Mar 19, 2024
| @@ -148,7 +148,7 @@ def make_pyramid(self, max_layers: int = 2, scale_z_axis: bool = True) -> List[n | |||
|
|
|||
| # For semantic segmentation masks we want to have a binary output. | |||
| # downscale_local_mean will return float array even for bool input with non-binary values | |||
| scaled = (downscale_local_mean(pyramid[i] == self.label, (z_scale, 2, 2)) > 0).astype(np.float32) | |||
| scaled = (downscale_local_mean(pyramid[i] == 1, (z_scale, 2, 2)) > 0).astype(np.int8) | |||
There was a problem hiding this comment.
Could this be just be pyramid?
manasaV3
approved these changes
Mar 20, 2024
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Outdated suggestions cannot be applied.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.
After the initial comparison with the label the maps are already binary, so after the scaling operation we need to compare with 1 instead of comparing with the label again.
Scaled masks are binary and should be stored as int8.
This PR fixes that.