Fix ingestion of segmentation masks #15
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
…, as this is the point where the labels are split.
uermel
commented
Feb 23, 2024
| @@ -71,7 +71,7 @@ def pyramid_to_mrc( | |||
| mrcfiles.append(os.path.basename(filename)) | |||
|
|
|||
| if write: | |||
| newfile = mrcfile.new(filename, self.data, overwrite=True) | |||
| newfile = mrcfile.new(filename, pyramid[0], overwrite=True) | |||
There was a problem hiding this comment.
Using the processed mask data instead of original data.
uermel
commented
Feb 23, 2024
Comment on lines
+173
to
+182
| if skip_header: | ||
| next(points) | ||
| for coord in points: | ||
| annotation_set.append( | ||
| self.point( | ||
| float(coord[coord_order[0]]), | ||
| float(coord[coord_order[1]]), | ||
| float(coord[coord_order[2]]), | ||
| ), | ||
| ) |
There was a problem hiding this comment.
Fix indentation so the file is actually open.
uermel
commented
Feb 23, 2024
| @@ -120,7 +120,8 @@ def __init__( | |||
|
|
|||
| def convert(self, fs: FileSystemApi, input_prefix: str, output_prefix: str, voxel_spacing: float = None): | |||
| input_file = self.get_source_file(fs, input_prefix) | |||
| return scale_maskfile(fs, self.get_output_filename(output_prefix), input_file, self.label, write=True) | |||
| return scale_maskfile(fs, self.get_output_filename(output_prefix), input_file, self.label, write=True, | |||
| voxel_spacing=voxel_spacing) | |||
There was a problem hiding this comment.
Add voxel_spacing override for segmentation masks.
manasaV3
reviewed
Feb 23, 2024
| ): | ||
| self.glob_string = glob_string.format(**glob_vars) | ||
| self.file_format = file_format | ||
| self.shape = shape | ||
| self.is_viz_default = is_viz_default | ||
| self.is_viz_default = is_visualization_default |
There was a problem hiding this comment.
Can we also rename the class variable to is_visualization_default for consistency?
There was a problem hiding this comment.
done with the last commit.
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.
Fixing chanzuckerberg/cryoet-data-portal#502
The labels in segmentation masks were not correctly separated because
pyramid_to_mrcincommon/image.pytook the original data, not the one from the pyramid (only the pyramid data is processed)AnnotationSource classes in
importers/annotation.pyexpected the keyword argumentis_viz_default, but the YAML dict hasis_visualization_defaultImport of
Pointannotations failed due to faulty indenting inPoint.loadinimporters/annotation.pyVoxel spacing of the ingested segmentation masks was not correct, because
scale_maskfileincommon/image.pywas not yet using the new override mechanism for thevoxel_spacing(the correctvoxel_spacingwas actually passed insideAnnotationImporter.import_annotations, but not taken into account in theSemanticSegmentationMaskFile.convertmethod.