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Outdated suggestions cannot be applied.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.
Describe your changes
Bump Tesseract version. Fix a couple of scanning issues. Use a custom trained model for Tesseract.
Issue or discord link
Testing/validation
See issues for test screenshots
I tested performance of default vs fast model vs best model (taken from InventoryKamera github)
Default is fastest, but not by much compared to fast model. The fast model has accurate feather level 20 detection. The best model is the slowest and also fails to detect the accurate mainstat for feathers. So I opted for using the fast model
Checklist before requesting a review (leave this PR as draft if any part of this list is not done.)
yarn run mini-ci
locally to validate format + lint.nx format write
to resolve them automatically.