Add inference API and task for all BioImage.IO Model Zoo models #338
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
qin-yu
added
enhancement
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #338 +/- ##
==========================================
- Coverage 65.25% 63.45% -1.81%
==========================================
Files 72 73 +1
Lines 5301 5442 +141
==========================================
- Hits 3459 3453 -6
- Misses 1842 1989 +147 ☔ View full report in Codecov by Sentry. |
for bioimageio.core blocked prediction
with broken types and returns
qin-yu
force-pushed
the
qy/unify-prediction
branch
from
316aa91 to
cf0e69b
Compare
|
|
|
@qin-yu the ci seems to be stuck |
PyTest finishes without error on macOS and Linux for me. Checking the CI now. |
|
For the record, starting with Python 3.13, |
|
I rerun the CI for main branch and it got stuck as well:
|
|
Tried some solutions but none works:
|
Now not only axes with `.id` and `.size` attributes but also string axes such as 'bcyx' coming with `shape` at the same level. These are due to the legacy of bioimage.io and complexity of versioning. Tested with `pioneering-rhino`
qin-yu
changed the title
qin-yu
force-pushed
the
qy/unify-prediction
branch
from
469aa6c to
fabae0a
Compare
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Outdated suggestions cannot be applied.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.
Add inference API and task for all BioImage.IO Model Zoo models
PlantSeg v2 supports training of our models and inference of all BioImage.IO models. This PR turns v2.0.0aX to v2.0.0b0.
Main features
I integrated support for bioimageio.core inference with BioImage.IO Model Zoo models into the PlantSeg API, tasks, and widgets.
To ensure functionality, I conducted the following manual tests:
1. 2D Input (YX): Tested with the
pioneering-rhinoPlantSeg model, resulting in a 2D image output.2. 3D Input (ZYX): Tested with the
emotional-cricketPlantSeg model, resulting in a 3D image output.3. 4D Input (CZYX): Tested with the
philosophical-pandaCellpose model, resulting in a sequence of 4D image outputs.The bioimageio.core Python package has multiple versions, requiring careful handling of format compatibility and extensive validation. Ongoing development of the library introduces additional complexity, but I believe this implementation addresses most use cases and version-specific challenges.
Screenshot
Multiple outputs of different sizes from Cellpose network:
List of BioImage.IO Model Zoo models: