Jurriaan Barkey Wolf

Just read your paper. Very interesting method! Thanks for open sourcing such a comprehensive codebase. My lab is interested in trying it on our own dataset for a classification task...

Document "SQL migration file: must start with '-- +goose Up'" (and not goose Down)

7

Hi there, thanks for this great tool! I noticed that new versions of Goose require SQL migration files to begin with the `-- +goose Up` statement. I made a few...

Added test cases containing a large in-the-wild image, and two rotated versions

5

One of the rotated versions fails (`test_wild_rotated_1`), likely because the QR code is too tilted. We don't have to retain the other two tests, as these cases are pretty much...

This project looks great! Thanks for the effort. I tried to run `demo.py` and ran into several dependency issues. Also, I would recommend that you fix the version numbers of...

Seems lik the `--no-default-features` flag (which disables Rayon multiprocessing) actually leads to a serious speedup of `detect()`, from ~1000 ms to ~700 ms on the `scientists.jpg` image. Likely due to...

This would have the same effect as making `processLineBreaksAsNewText` defaulting to true, but with reduced code complexity. I think merging this change would constitute a (small) breaking change.

Optimised inference pipeline

5

Hi all, First of all, thanks for this amazing project. Our lab is really happy to be able to use it, and I've learned a lot from working with it....