Merged
Conversation
hansent
commented
Mar 13, 2025
| type: Literal["roboflow_core/detections_merge@v1"] | ||
| predictions: Selector( | ||
| kind=[ | ||
| OBJECT_DETECTION_PREDICTION_KIND, |
Collaborator
Author
There was a problem hiding this comment.
not sure if this should be only
OBJECT_DETECTION_PREDICTION_KIND and INSTANCE_SEGMENTATION_PREDICTION_KIND (tested with those two), but I think KEYPOINT_DETECTION_PREDICTION_KIND should also be OK / we have bounding box info via detections?
hansent
requested review from
PawelPeczek-Roboflow,
grzegorz-roboflow,
probicheaux and
yeldarby
as code owners
hansent
commented
Mar 14, 2025
| else None | ||
| ), | ||
| class_id=( | ||
| np.array([predictions.class_id[0]], dtype=np.int32) |
Collaborator
Author
There was a problem hiding this comment.
picking one of the classes here. other options might be:
- use. hardcoded class like "merged_detections", but seem odd to introduce a special classname / could potentially conflict with other class named the same
- although could make this configurable also as a property
- use the most common one?
I think use cases probably mostly for getting the box coordiantes and class wont matter
Collaborator
There was a problem hiding this comment.
I think if we merge everything then maybe most common class name would make sense, but maybe we should produce as many detections as many classes we have?
grzegorz-roboflow
previously approved these changes
Mar 14, 2025
grzegorz-roboflow
approved these changes
Mar 14, 2025
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Adds a DetectionsMerge block that can be used to merge several detections into a single object detection bounding box. E.g. to crop section of image containing all detections.
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
unit tests
Any specific deployment considerations
n/a
Docs
added via workflows gallery build decorator