Refactor Prediction App to include extended annotation workflow#14
Open
maartenpaul wants to merge 8 commits into
Open
Refactor Prediction App to include extended annotation workflow#14maartenpaul wants to merge 8 commits into
maartenpaul wants to merge 8 commits into
Conversation
Replace PredictionApp with AnnotateApp featuring manifest-based annotation set management, GeoJSON persistence, configurable annotation workflow, and training integration. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add annotate_ai_views (manifest CRUD, GeoJSON persistence), training_views (SLURM training integration), and sam_views. Update urls.py, apiService.js, and index.js routing. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…tches is true Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Convert annotation overlay from Canvas to SVG for vector-quality rendering at any zoom level (non-scaling-stroke) - Fix random Z-slice and timepoint selection (was always z=0) - Add n_slices/n_timepoints UI inputs for random mode - Distribute patches round-robin across z/t combinations - Make patches enabled by default with helper text and tooltips - Add percentile-based image normalization (compute_normalization endpoint) - Add normalization config to ConfigureTab (percentile low/high) - Auto-apply normalization in AnnotateViewer when loading images - Fix validate button to not create annotation sets - Lock Annotate tab navigation with warning when set is active - Make unit list scrollable, thinner SVG strokes, smaller SAM points Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
maartenpaul
requested review from
Copilot and
pmkrawczyk
and removed request for
Copilot
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
1 participant
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.
This pull request introduces several significant improvements and new features to the OMERO.biomero project for support for advanced annotation and training workflows. The main changes are summarized below.
Backend and Integration Enhancements:
omero-init.shto improve container initialization:omero_annotate_aiandOMERO.biomeroin editable mode for faster development.stardist_train.py, which submits a SLURM job to train a Stardist model. This script handles parameter validation, SLURM batch script creation, and job submission, enabling scalable model training from within OMERO.Annotation and Prediction Features:
sam_views.py, providing backend endpoints for MobileSAM-based interactive segmentation:/set_imageand/predictendpoints for frontend integration, supporting point and box prompts and returning polygon results.get_image_channelsendpoint inprediction_views.pyto include detailed channel windowing information (start,end,min,max), supporting more precise image rendering and normalization on the frontend.These changes collectively improve the developer experience, enable advanced annotation workflows, and streamline training and prediction pipelines within the OMERO.biomero ecosystem.
@pmkrawczyk @RAHoebe Can you have a look at this. I tried to implement my annotation app on top of training branch. Please check if you can deploy it and let's discuss possible issues and improvements. Then we could merge this into the train branch to subsequently merge into main.