New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Full image annotation for Sparse training image throws errors for detections #1443
Comments
Quick addition. Defining an area using a polygon no longer works for the in-built detection, just when running a stardist script:
|
#1465 should fix the first issue. About:
I wasn't able to reproduce the error. Does it happens on every run? Is it possible to share the project throwing the error? |
Bug report
Describe the bug
When optimising perameters for a project by creating a sparse composite image from different image entries. When running cell detection using script editor, errors are generated for the final tiles IF the entire shape is not a perfect rectangle. If using stardist script for cell detection, errors are generated before any detections.
Can avoid both by manual annotation with a polygon tool to follow image boundaries -> so not sure if a crucial bug. Carried over from last release to v5.
To Reproduce
Steps to reproduce the behavior:
Expected behavior
To recognise bounds or the image in "create full image annotation" command, excluding what the error is calling "null" regions
Screenshots
Desktop (please complete the following information):
Additional context
Same issue was present in previous version (0.4.4)
The text was updated successfully, but these errors were encountered: