Update evaluation scripts#1186
Merged
Merged
Conversation
* Add interactive, automatic and joint training scripts * Remove stale code and increase evaluation pool * Remove weird linting artifacts * Make evaluation pipeline more robust and improve 3d interactive interface for sam2 * Add more changes for making evaluation work * Update slurm submission scripts * Add more changes for joint training * Make batches shardable across multiple GPUs * Add download check scripts for missing datasets
* Add grid search scripts for postprocessing * Fix blockwise MC --------- Co-authored-by: Constantin Pape <constantin.pape@informatik.uni-goettingen.de>
…ional-cell-analytics/micro-sam into add-evaluation-backbone
* Start debugging interactive segmentation training * Add scripts for debugging 3d evaluation * More changes to match evaluation with training * Switch flow computation to bioimage-cpp backend and make choice modular * Add multiple changes in training and evaluation design * Add more datasets and adjust visualize.py for viewing * Update microns roi for segmentation * Align more visuals to mitoem * Evaluate debugging scripts on bigger pool of data * Make training work for random frame prompting and bidirectional propagation * Improve prompting strategy for training * Update training raw input range checks * Temporary pin for elf to let tests run * Add deterministic SAM2 validation and finalie generalist interactive model training config * Conclude results for interactive training debug
* Add custom loss and metric to simply interactive training * Align joint training with interactive segemntation improvements
Collaborator
Author
|
My quick thought here is to go ahead and merge this. I can do a solid refactor later for other things! |
Collaborator
Author
|
Since the parent working branch (#1196) got merged to |
Contributor
|
Yes, let's go ahead with this. (We should just make sure not to merge anything related to SAM2 onto |
Collaborator
Author
|
Bingo. We should stick to our current I'll go ahead and merge this then! |
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.
This PR aims to update evaluation scripts to adopt
micro_sam2backbone. This is gonna be a long WIP, so I'll take care of things one by one here itself! ;)